{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:58:55Z","timestamp":1774663135382,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698936","type":"print"},{"value":"9789819698943","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9894-3_2","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T19:56:35Z","timestamp":1753473395000},"page":"15-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LERO: LLM-driven Evolutionary Framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yuan","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohan","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianmin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"issue":"2","key":"2_CR1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1162\/evco_a_00325","volume":"31","author":"THW Back","year":"2023","unstructured":"Back, T.H.W., et al.: Evolutionary algorithms for parameter optimization\u2014thirty years later. Evol. Comput. 31(2), 81\u2013122 (2023)","journal-title":"Evol. Comput."},{"key":"2_CR2","volume-title":"Survey on large language model-enhanced reinforcement learning: Concept, taxonomy, and methods. arXiv preprint arXiv:2404.00282","author":"Y Cao","year":"2024","unstructured":"Cao, Y., et al.: Survey on large language model-enhanced reinforcement learning: Concept, taxonomy, and methods. arXiv preprint arXiv:2404.00282 (2024)"},{"key":"2_CR3","volume-title":"Multi-objective optimization using evolutionary algorithms","author":"K Deb","year":"2001","unstructured":"Deb, K.: Multi-objective optimization using evolutionary algorithms John Wiley & Sons Ltd, New York (2001)"},{"key":"2_CR4","volume-title":"Genetic Algorithms in Search Optimization and Machine Learning","author":"DE Goldberg","year":"1988","unstructured":"Goldberg, D.E.: Genetic Algorithms in Search Optimization and Machine Learning (1988), https:\/\/api.semanticscholar.org\/CorpusID:38613589"},{"issue":"7626","key":"2_CR5","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. Nature. 538(7626), 471\u2013476 (2016)","journal-title":"Nature"},{"key":"2_CR6","volume-title":"2015 AAAI Fall Symposium Series","author":"M Hausknecht","year":"2015","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable MDPs. In: 2015 AAAI Fall Symposium Series (2015)"},{"key":"2_CR7","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"C Kim","year":"2023","unstructured":"Kim, C., et al.: Guide your agent with adaptive multimodal rewards. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"2_CR8","first-page":"7211","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7211\u20137218 (2020)"},{"key":"2_CR9","volume-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)","author":"R Lowe","year":"2017","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems 30 (NIPS 2017) (2017)"},{"key":"2_CR10","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"YJ Ma","year":"2024","unstructured":"Ma, Y.J., et al.: Eureka: Human-level reward design via coding large language models. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"issue":"5","key":"2_CR11","doi-asserted-by":"publisher","DOI":"10.1527\/tjsai.36-5_AG21-H","volume":"36","author":"N Matsunami","year":"2021","unstructured":"Matsunami, N., Okuhara, S., Ito, T.: Reward design for multi-agent reinforcement learning with a penalty based on the payment mechanism. Trans. Jpn. Soc. Artif. Intell. 36(5), AG21\u2013H_1\u201311 (2021)","journal-title":"Trans. Jpn. Soc. Artif. Intell."},{"key":"2_CR12","unstructured":"Paischer, F., Adler, T., Hofmarcher, M., Hochreiter, S.: Semantic HELM: A human-readable memory for reinforcement learning. Adv. Neural Inf. Proces. Syst. 36 (2024)"},{"key":"2_CR13","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"A Radford","year":"2021","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"178","key":"2_CR14","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(178), 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"2_CR15","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/s10458-022-09580-8","volume":"36","author":"J Sheng","year":"2022","unstructured":"Sheng, J., et al.: Learning structured communication for multi-agent reinforcement learning. Auton. Agent. Multi-Agent Syst. 36(2), 50 (2022)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"2_CR16","volume-title":"Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296","author":"P Sunehag","year":"2017","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"2_CR17","first-page":"23417","volume-title":"Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research (PMLR)","author":"L Wang","year":"2022","unstructured":"Wang, L., et al.: Individual reward assisted multi-agent reinforcement learning. In: Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research (PMLR), vol. 162, pp. 23417\u201323432 (2022)"},{"key":"2_CR18","first-page":"51484","volume-title":"Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research (PMLR)","author":"Y Wang","year":"2024","unstructured":"Wang, Y., et al.: RL-VLM-F: Reinforcement learning from vision language foundation model feedback. In: Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research (PMLR), vol. 235, pp. 51484\u201351501 (2024)"},{"key":"2_CR19","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"T Xie","year":"2024","unstructured":"Xie, T., et al.: Text2reward: Reward shaping with language models for reinforcement learning. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"2_CR20","volume-title":"Neural Information Processing Systems","author":"C Yu","year":"2021","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., Bayen, A.M., Wu, Y.: The surprising effectiveness of ppo in cooperative multi-agent games. In: Neural Information Processing Systems (2021) https:\/\/api.semanticscholar.org\/CorpusID:232092445"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9894-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:35:05Z","timestamp":1774661705000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9894-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698936","9789819698943"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9894-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}